Agent Skills

---

name: implementing-command-palettes

description: Use when building Cmd+K command palettes in React - covers keyboard navigation with arrow keys, keeping selected items in view with scrollIntoView, filtering with shortcut matching, and preventing infinite re-renders from reference instability

---

name: orchestrating-agent-relay

description: The canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.

---

name: orchestrating-agent-relay

description: The canonical way to run agent-relay - self-bootstrap the local broker and autonomously spawn, monitor, and coordinate a team of worker agents without human intervention. Covers infrastructure startup, agent spawning, lifecycle monitoring, message-based reading via the relay MCP, and team coordination.

---

name: prpm-json-best-practices

description: Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format, eager/lazy activation, and conversion hints

---

name: relay-80-100-workflow

description: Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.

---

name: relay-80-100-workflow

description: Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.

---

name: review-animations

description: Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

---

name: review-fix-signoff-loop

description: Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.

---

name: review-fix-signoff-loop

description: Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.

---

name: search-shared-sessions

description: Search an Agent Relay workspace's shared coding-agent sessions for prior work, decisions, fixes, or the context behind a task or pull request. Use when team history could answer the user's question or prevent repeating an investigation.

---

name: setting-up-relayfile

description: Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a local mount. Covers `relayfile setup`, dynamic integration discovery with `relayfile integration available/search`, Nango and Composio backend selection, Atlassian site selection and metadata, cloud login, OAuth/connect flows, mount verification, `RELAYFILE_LOCAL_DIR` handoff, writeback status and retry commands, and key May 2026 cloud-mount gotchas.

---

name: setting-up-relayfile

description: Use when an agent or human needs to set up relayfile end-to-end so agents can read and write provider files through a local mount. Covers `relayfile setup`, dynamic integration discovery with `relayfile integration available/search`, Nango and Composio backend selection, Atlassian site selection and metadata, cloud login, OAuth/connect flows, mount verification, `RELAYFILE_LOCAL_DIR` handoff, writeback status and retry commands, and key May 2026 cloud-mount gotchas.

---

name: using-agent-relay

description: Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.

---

name: using-agent-relay

description: Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.

---

name: writing-relayflows

description: Use when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is `flows`, package versions 2.0.x) in TypeScript or YAML/JSON. Covers the three-rung ladder (run/llm/agent), the resident verbs (human/dispatch/done), verification gates, TypeScript vs YAML authoring, per-step cli/model selection and its resolution order, flows.json, and `flows check`/`run`/`resume` with their real refusal shapes and exit codes. Not for the older, unrelated `@relayflows/core` WorkflowBuilder engine (`.pattern('dag')`/.agent()/.step() chains) that `writing-agent-relay-workflows` and `migrating-persona-to-relayflow` cover — that's a different product despite the similar name.

---

name: writing-relayflows

---

name: administrative-value-judgment

description: 辅助中国大陆行政机关法律工作人员，根据一段行政案情，按行政法基本原则进行价值判断、利益衡量，并形成倾向性裁量结论。

---

name: analogical-reasoning

description: 当AI智能体需要处理以下情形时触发本技能： 1. 当前案件/问题在现行法律中没有直接、明确的规定（法律漏洞）； 2. 需要参考已有判例、相似案件或相近法律规范来推导当前问题的处理方案； 3. 用户明确要求"参照""比照""类推适用"某一规范或案例； 4. 在法律论证中需要以"相似案件相似处理"（Like cases should be treated alike）原则支撑结论； 5. 需要评估两个或多个案件/规范之间的相似性与差异性，以判断能否进行类比； 6. 在合同解释、侵权责任认定、行政处罚裁量等场景中，需要借助类似情形的处理经验形成论证。 本技能的核心是：识别相似性基础（tertium comparationis），论证类比的正当性，并在此基础上得出合理的法律结论。

---

name: api-tester

description: 依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时；区分“生成测试”和“执行请求”的授权，不猜测状态码、响应结构或 SLA，不在未确认环境中发送写请求。

---

name: argument-chain-construction

description: 当AI智能体需要将法律推理结果组织为完整、自洽、有说服力的论证结构时触发此技能。 典型触发场景包括但不限于： - 撰写法律意见书、代理词、辩护词、答辩状等法律文书中的论证部分 - 回答用户提出的复杂法律问题，需要多步骤推理并呈现结论 - 对争议焦点进行系统性分析，需要构建从事实到法律到结论的完整推理路径 - 反驳对方观点时，需要构建替代性论证链条 - 对多个法律问题进行综合分析，需要确保各论证之间逻辑一致、互不矛盾 - 在法律研究备忘录中呈现分析结论 触发信号关键词：论证、分析、推理、为什么、证明、理由、论述、阐述观点、法律分析

---

name: argument-strength-evaluation

description: 当AI智能体完成一段法律推理或论证后，需要对该推理结论进行自我评估，判断论证的整体强度与置信度，识别并标注推理链条中的薄弱环节。 触发条件包括但不限于： - 完成法律分析后需要给出结论可靠性评级 - 用户明确要求评估某一论证的说服力或可靠性 - 存在多个竞争性法律解释需要比较论证强度 - 推理过程中涉及不确定因素（事实不明、法律空白、争议观点）需要标注 - 为决策者提供风险提示，说明结论的局限性 - 对己方或对方的法律论证进行攻防强度评估 - 在法律意见书、备忘录等文书中需要附加置信度说明

---

name: billing-and-litigation-budget

description: 当用户需要统计、管理律师工时、专家费用、调查费用，控制诉讼成本、向客户出具工时单或费用单时使用此技能。 典型触发场景包括但不限于： - 提到"工作小时""专家费用""调查费用""办案成本""工时单""费用单""预算""成本控制"等关键词 - 询问某一律师的工作小时、某一案件的办案费用或诉讼成本时 - 用户要求交付律师工作时长总结或办案工时单、办案费用单，用于交付客户或申请报销时 - 需要对某一案件或常法服务进行预算编制、预算执行监控或预算偏差分析时 - 需要评估诉讼成本与预期收益，进行诉讼经济性分析时

---

name: case-lifecycle-planning

description: 案件全周期规划技能。当用户需要规划案件准备时间线、创建或询问案件准备时间节点、生成案件诉讼路线图和关键时间一览表时触发。典型触发关键词："案件准备""案件准备规划""案件准备时间线""规划案件准备节奏""排开庭"。不处理案件向律师的分配，也不处理与案件管理无关的一般性编程任务。

---

name: case-retrieval

description: 当用户需要查找与当前法律问题相关的类似案例、相关判决、裁判规则时触发此技能。典型触发场景包括：用户明确要求查找类似案例或判例；需要通过既往裁判支撑法律论点；进行案件预判需要参考同类判决；撰写法律文书需要引用权威案例；分析某一法律问题的司法实践趋势；对比不同法院、不同时期对同一问题的裁判立场。关键词包括但不限于：类似案例、相关判决、判例检索、裁判规则、同类案件、指导性案例、典型案例、司法观点、裁判要旨等。